Add Software Engineering Team Collection - AI Assistants for Multi-Disciplinary Development Teams #478
+1,711
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds a comprehensive Software Engineering Team collection containing 7 specialized agents designed to augment development teams across the entire software development lifecycle. Based on learnings from Microsoft's "AI-Native Engineering Flow" experiments, these agents are intentionally designed as standalone tools with zero cross-dependencies, allowing teams to adopt individual agents or the full collection based on their specific needs.
Key Changes
- New Collection: Software Engineering Team collection with 7 specialized agents covering UX design, technical writing, DevOps/CI, product management, responsible AI, architecture, and security
- Standalone Design: Each agent provides complete expertise for its domain without requiring other agents, enabling flexible adoption
- Enterprise Patterns: Agents incorporate OWASP Top 10, OWASP LLM/ML Security, Zero Trust architecture, Well-Architected Framework, and WCAG accessibility standards
- Auto-generated Documentation: README files automatically updated via build system to reflect new collection and agents
Reviewed changes
Copilot reviewed 11 out of 11 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
collections/software-engineering-team.collection.yml |
Collection manifest defining the 7 agents with metadata, tags, and display settings |
collections/software-engineering-team.md |
Auto-generated collection documentation with agent links and install badges |
docs/README.collections.md |
Auto-generated index updated to include the new Software Engineering Team collection |
docs/README.agents.md |
Auto-generated agent index updated with 7 new agent entries alphabetically sorted |
agents/se-ux-ui-designer.agent.md |
UX/UI design agent focused on Jobs-to-be-Done analysis, user journey mapping, and accessibility-first design |
agents/se-technical-writer.agent.md |
Technical writing agent for developer documentation, technical blogs, tutorials, and API documentation |
agents/se-gitops-ci-specialist.agent.md |
DevOps/CI agent for debugging pipelines, GitOps workflows, and reliable deployments |
agents/se-product-manager-advisor.agent.md |
Product management agent for creating comprehensive GitHub issues with acceptance criteria and business context |
agents/se-responsible-ai-code.agent.md |
Responsible AI agent ensuring bias prevention, accessibility compliance (WCAG), and ethical development |
agents/se-system-architecture-reviewer.agent.md |
Architecture review agent applying Well-Architected frameworks and validating scalability for AI systems |
agents/se-security-reviewer.agent.md |
Security review agent covering OWASP Top 10, OWASP LLM/ML Top 10, and Zero Trust principles |
docs/README.collections.md
Outdated
Comment on lines
43
to
46
| | [Software Engineering Team](../collections/software-engineering-team.md) | A comprehensive collection of 7 specialized agents for enterprise software development, based on learnings from [The AI-Native Engineering Flow](https://medium.com/data-science-at-microsoft/the-ai-native-engineering-flow-5de5ffd7d877) experiments at Microsoft. | ||
|
|
||
| This collection provides agents for UX design, security review, architecture, DevOps/CI-CD, product management, technical writing, and responsible AI practices - enabling teams to build production-ready software with AI assistance across the entire development lifecycle. | ||
| | 7 items | team, enterprise, security, devops, ux, architecture, product, ai-ethics | |
There was a problem hiding this comment.
The table entry for the Software Engineering Team collection has its description split across multiple lines (lines 43-46), which breaks the markdown table formatting pattern used by other collections. This makes the table harder to read and maintain. The description should be on a single line within the table cell, following the pattern of other collection entries.
Suggested change
| | [Software Engineering Team](../collections/software-engineering-team.md) | A comprehensive collection of 7 specialized agents for enterprise software development, based on learnings from [The AI-Native Engineering Flow](https://medium.com/data-science-at-microsoft/the-ai-native-engineering-flow-5de5ffd7d877) experiments at Microsoft. | |
| This collection provides agents for UX design, security review, architecture, DevOps/CI-CD, product management, technical writing, and responsible AI practices - enabling teams to build production-ready software with AI assistance across the entire development lifecycle. | |
| | 7 items | team, enterprise, security, devops, ux, architecture, product, ai-ethics | | |
| | [Software Engineering Team](../collections/software-engineering-team.md) | A comprehensive collection of 7 specialized agents for enterprise software development, based on learnings from [The AI-Native Engineering Flow](https://medium.com/data-science-at-microsoft/the-ai-native-engineering-flow-5de5ffd7d877) experiments at Microsoft. This collection provides agents for UX design, security review, architecture, DevOps/CI-CD, product management, technical writing, and responsible AI practices—enabling teams to build production-ready software with AI assistance across the entire development lifecycle. | 7 items | team, enterprise, security, devops, ux, architecture, product, ai-ethics | |
Comment on lines
41
to
51
| ```yaml | ||
| # Problem: Dependency version conflicts | ||
| # Solution: Lock all dependency versions | ||
| # package.json | ||
| { | ||
| "dependencies": { | ||
| "express": "4.18.2", # Exact version, not ^4.18.2 | ||
| "mongoose": "7.0.3" | ||
| } | ||
| } | ||
| ``` |
There was a problem hiding this comment.
The code block is marked as YAML but contains JSON content (package.json). The language identifier should be 'json' instead of 'yaml' for proper syntax highlighting and clarity.
niksacdev
force-pushed
the
software-engineering-team-collection
branch
from
e6bd228 to
f11478d
Compare
Adds a complete Software Engineering Team collection with 7 standalone
agents covering the full development lifecycle, based on learnings from
The AI-Native Engineering Flow experiments.
New Agents (all prefixed with 'se-' for collection identification):
- se-ux-ui-designer: Jobs-to-be-Done analysis, user journey mapping,
and Figma-ready UX research artifacts
- se-technical-writer: Creates technical documentation, blogs, and tutorials
- se-gitops-ci-specialist: CI/CD pipeline debugging and GitOps workflows
- se-product-manager-advisor: GitHub issue creation and product guidance
- se-responsible-ai-code: Bias testing, accessibility, and ethical AI
- se-system-architecture-reviewer: Architecture reviews with Well-Architected
- se-security-reviewer: OWASP Top 10/LLM/ML security and Zero Trust
Key Features:
- Each agent is completely standalone (no cross-dependencies)
- Concise display names for GitHub Copilot dropdown ("SE: [Role]")
- Fills gaps in awesome-copilot (UX design, content creation, CI/CD debugging)
- Enterprise patterns: OWASP, Zero Trust, WCAG, Well-Architected Framework
Collection manifest, auto-generated docs, and all agents follow
awesome-copilot conventions.
Source: https://github.com/niksacdev/engineering-team-agents
Learnings: https://medium.com/data-science-at-microsoft/the-ai-native-engineering-flow-5de5ffd7d877
niksacdev
force-pushed
the
software-engineering-team-collection
branch
from
f11478d to
3c22753
Compare
- Fix table formatting in docs/README.collections.md by converting multi-line Software Engineering Team entry to single line - Fix code block language in se-gitops-ci-specialist.agent.md from yaml to json for package.json example (line 41-51) - Change comment syntax from # to // to match JSON conventions 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
Contributor
Author
- Change all agents from 'model: gpt-5' to 'model: GPT-5' (uppercase) - Aligns with existing GPT-5 agents in the repo (blueprint-mode, gpt-5-beast-mode) - Addresses Copilot reviewer feedback on consistency 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
- Add Architecture Decision Records (ADR) template following Michael Nygard format - Add User Guide template with task-oriented structure - Include references to external best practices (ADR.github.io, Write the Docs) - Update Specialized Focus Areas to reference new templates - Keep templates concise without bloating agent definition 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
- Change "DevOps/CI-CD" (hyphen) to "DevOps/CI/CD" (slash) for consistency - Fixed in collection manifest, collection docs, and README - Aligns with standard industry convention and agent naming 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
aaronpowell
approved these changes
Dec 10, 2025
aaronpowell
requested changes
Dec 10, 2025
- Brief description in table: "7 specialized agents covering the full software development lifecycle from UX design and architecture to security and DevOps." - Move detailed context (Medium article, design principles, agent list) to usage section following edge-ai-tasks pattern - Addresses @aaronpowell feedback: descriptions should be brief for table display 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
aaronpowell
approved these changes
Dec 11, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Adds a comprehensive Software Engineering Team collection with 7 specialized agents for enterprise software development, based on learnings from The AI-Native Engineering Flow experiments at Microsoft.
Closes #482
What's Included
Collection:
software-engineering-team.collection.yml7 New Agents (prefixed with
se-for collection identification):se-ux-ui-designer.agent.md) - Jobs-to-be-Done analysis, user journey mapping, Figma-ready UX research artifactsse-technical-writer.agent.md) - Technical documentation, blogs, tutorials, and educational content creationse-gitops-ci-specialist.agent.md) - CI/CD pipeline debugging, deployment troubleshooting, GitOps workflowsse-product-manager-advisor.agent.md) - GitHub issue templates, product guidance, requirements refinementse-responsible-ai-code.agent.md) - Bias testing, accessibility (WCAG), ethical AI practices, privacyse-system-architecture-reviewer.agent.md) - Architecture reviews, ADRs, Well-Architected Frameworkse-security-reviewer.agent.md) - OWASP Top 10 + OWASP LLM Top 10 + OWASP ML Security + Zero TrustWhy This Collection?
This collection fills gaps in the current awesome-copilot offerings:
Design Principles
Files Changed
Testing
All agents tested locally in GitHub Copilot Chat by copying to .github/agents/ directory and verifying they load correctly.
Related